feat: revert backend to use sentence-transformers (all-MiniLM-L6-v2) for better embeddings

fix: update Python base image to 3.11 for thinc compatibility

build: add rust compiler to fix fastembed pip install error

chore: add huggingface configuration block to readme

feat: add Dockerfile for Hugging Face Spaces deployment

refactor: replace memory-heavy PyTorch with fastembed (ONNX) to fix OOM

perf: limit in-memory corpus to 5k docs to prevent OOM on 512MB free tier

fix: precompute dense embeddings to prevent OOM on render

chore: remove local planning and presentation files from tracking

chore: force CPU-only PyTorch installation

update readme for query

ignore local planning files, add readme links

docs: add live demo link to README

deployment ready

propbank data add

Initial commit